tam-market-sizing-agent
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill establishes a surface for indirect prompt injection by instructing the agent to research and analyze data from external sources such as industry reports (e.g., McKinsey, BCG) and financial databases (e.g., Statista) as defined in SKILL.md.
- Ingestion points: External market research reports, financial databases, and government sources.
- Boundary markers: Absent; the skill lacks instructions for the agent to use delimiters or to ignore potential instructions embedded in the external reports.
- Capability inventory: Minimal; the skill consists of natural language instructions and does not explicitly request the use of high-privilege tools, shell execution, or network write operations.
- Sanitization: Absent; there is no mention of filtering, validating, or escaping the content retrieved from external sources before analysis.
Audit Metadata